Llama 256 12L is an open-source language model by stage-babylm. Features: 9.9m LLM, Context: 2K, LLM Explorer Score: 0.31.
| LLM Name | Llama 256 12L |
| Repository π€ | https://huggingface.co/stage-babylm/llama-256-12L |
| Model Size | 9.9m |
| Required VRAM | 0 GB |
| Updated | 2026-08-24 |
| Maintainer | stage-babylm |
| Model Type | llama |
| Model Files | |
| Model Architecture | LlamaForCausalLM |
| Context Length | 2048 |
| Model Max Length | 2048 |
| Transformers Version | 5.14.1 |
| Tokenizer Class | TokenizersBackend |
| Padding Token | [PAD] |
| Vocabulary Size | 1001 |